Need help with Realtime_Multi-Person_Pose_Estimation?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

4.7K Stars 1.4K Forks Other 162 Commits 105 Opened issues


Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Services available


Need anything else?

Contributors list

Realtime Multi-Person Pose Estimation

By Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh.


Code repo for winning 2016 MSCOCO Keypoints Challenge, 2016 ECCV Best Demo Award, and 2017 CVPR Oral paper.

Watch our video result in YouTube or our website.

We present a bottom-up approach for realtime multi-person pose estimation, without using any person detector. For more details, refer to our CVPR'17 paper, our oral presentation video recording at CVPR 2017 or our presentation slides at ILSVRC and COCO workshop 2016.

This project is licensed under the terms of the license.

Other Implementations

Thank you all for the efforts for the reimplementation! If you have new implementation and want to share with others, feel free to make a pull request or email me! - Our new C++ library OpenPose (testing only) - Tensorflow [version 1] | [version 2] | [version 3] | [version 4] | [version 5] | [version 6] | [version 7 - TF2.1] - Pytorch [version 1] | [version 2] | [version 3] - Caffe2 [version 1] - Chainer [version 1] - MXnet [version 1] - MatConvnet [version 1] - CNTK [version 1]


  1. Testing
  2. Training
  3. Citation


C++ (realtime version, for demo purpose)

  • Please use OpenPose, now it can run in CPU/ GPU and windows /Ubuntu.
  • Three input options: images, video, webcam

Matlab (slower, for COCO evaluation)

  • Compatible with general Caffe. Compile matcaffe.
  • Run
    cd testing;
    to retrieve our latest MSCOCO model from our web server.
  • Change the caffepath in the
    and run
    for an example usage.


  • cd testing/python
  • ipython notebook
  • Open
    and execute the code


Network Architecture


Training Steps

  • Run
    cd training; bash
    to obtain the COCO images in
    , keypoints annotations in
    and COCO official toolbox in
  • Run
    in matlab to convert the annotation format from json to mat in
  • Run
    in matlab to obatin the mask images for unlabeled person. You can use 'parfor' in matlab to speed up the code.
  • Run
    to generate a json file in
    folder. The json files contain raw informations needed for training.
  • Run
    to generate your LMDB. (You can also download our LMDB for the COCO dataset (189GB file) by:
  • Download our modified caffe: caffe_train. Compile pycaffe. It will be merged with caffe_rtpose (for testing) soon.
  • Run
    python --exp 1
    to generate the prototxt and shell file for training.
  • Download VGG-19 model, we use it to initialize the first 10 layers for training.
  • Run
    bash 0,1
    (generated by to start the training with two gpus.


Please cite the paper in your publications if it helps your research:

  author = {Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh},
  booktitle = {CVPR},
  title = {Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields},
  year = {2017}

@inproceedings{wei2016cpm, author = {Shih-En Wei and Varun Ramakrishna and Takeo Kanade and Yaser Sheikh}, booktitle = {CVPR}, title = {Convolutional pose machines}, year = {2016} }

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.